# Steering Code LLMs with Activation Directions for Language and Library Control

arXiv: https://arxiv.org/abs/2603.23629 · HTML: https://mlsanity.com/paper/2603.23629/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 9 references that are in the map.
- First posted on arXiv 24 Mar 2026.

## Builds on (most cited first, 8 of 8)

- [Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)](https://mlsanity.com/paper/1711.11279/) (2017)
- [Steering Llama 2 via Contrastive Activation Addition](https://mlsanity.com/paper/2312.06681/) (2023)
- [Refusal in Language Models Is Mediated by a Single Direction](https://mlsanity.com/paper/2406.11717/) (2024)
- [Steering Language Models With Activation Engineering](https://mlsanity.com/paper/2308.10248/) (2023)
- [Programming Refusal with Conditional Activation Steering](https://mlsanity.com/paper/2409.05907/) (2024)
- [Improving Instruction-Following in Language Models through Activation Steering](https://mlsanity.com/paper/2410.12877/) (2024)
- [A Study of LLMs' Preferences for Libraries and Programming Languages](https://mlsanity.com/paper/2503.17181/) (2025)
- [ODESteer: A Unified ODE-Based Steering Framework for LLM Alignment](https://mlsanity.com/paper/2602.17560/) (2026)

## Built on by (most cited first, 1 of 1)

- [LLMs program using Reusable and Composable Abstract Representations](https://mlsanity.com/paper/2610.19238/) (2026)

## Abstract (arXiv)

Code LLMs often default to particular programming languages and libraries under neutral prompts. We investigate whether these preferences are encoded as approximately linear directions in activation space that can be manipulated at inference time. Using a difference-in-means method, we estimate layer-wise steering vectors for five language/library pairs and add them to model hidden states during generation. Across three open-weight code LLMs, these interventions substantially increase generation toward the target ecosystem under neutral prompts and often remain effective even when prompts explicitly request the opposite choice. Steering strength varies by model and target, with common ecosystems easier to induce than rarer alternatives, and overly strong interventions can reduce output quality. Overall, our results suggest that code-style preferences in LLMs are partly represented by compact, steerable structure in activation space.